Image de couverture de livre

Reducing the GPU Memory Bottleneck with Lossless Compression for ML -- Extended

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kamath, Aditya K, Krishnamurthy, Arvind, Canini, Marco, Peter, Simon
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Distributed, Parallel, and Cluster Computing I.2.7; C.1.4; E.4
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference
par: Kamath, Aditya K, et autres
Publié: (2024)

Rotary GPU: Exploring Local Execution Paths for Large Mixture-of-Experts Models Under Limited GPU Memory
par: Jo, Myeong Jun
Publié: (2026)

Parallelization Strategies for Dense LLM Deployment: Navigating Through Application-Specific Tradeoffs and Bottlenecks
par: Topcu, Burak, et autres
Publié: (2026)

MAS-Attention: Memory-Aware Stream Processing for Attention Acceleration on Resource-Constrained Edge Devices
par: Shakerdargah, Mohammadali, et autres
Publié: (2024)

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models
par: Lo, Yun-Chen, et autres
Publié: (2024)

Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference
par: Ganjihal, Sanjeev Rao
Publié: (2026)

ATTNChecker: Highly-Optimized Fault Tolerant Attention for Large Language Model Training
par: Liang, Yuhang, et autres
Publié: (2024)

Comparative Analysis of Large Language Model Inference Serving Systems: A Performance Study of vLLM and HuggingFace TGI
par: Kolluru, Saicharan
Publié: (2025)

Training LLMs on HPC Systems: Best Practices from the OpenGPT-X Project
par: Penke, Carolin, et autres
Publié: (2025)

Architecture-Aware LLM Inference Optimization on AMD Instinct GPUs: A Comprehensive Benchmark and Deployment Study
par: Georgiou, Athos
Publié: (2026)

SparkAttention: High-Performance Multi-Head Attention for Large Models on Volta GPU Architecture
par: Xu, Youxuan, et autres
Publié: (2025)

Addressing tokens dynamic generation, propagation, storage and renewal to secure the GlideinWMS pilot based jobs and system
par: Coimbra, Bruno Moreira, et autres
Publié: (2025)

Kant: An Efficient Unified Scheduling System for Large-Scale AI Clusters
par: Zeng, Lingling, et autres
Publié: (2025)

Parameter-Efficient and Personalized Federated Training of Generative Models at the Edge
par: Khan, Kabir, et autres
Publié: (2025)

Flex-MIG: Enabling Distributed Execution on MIG
par: Kim, Myeongsu, et autres
Publié: (2025)

Towards Building Private LLMs: Exploring Multi-Node Expert Parallelism on Apple Silicon for Mixture-of-Experts Large Language Model
par: Chen, Mu-Chi, et autres
Publié: (2025)

GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration
par: Sarker, Yeahia, et autres
Publié: (2026)

DSDE: Dynamic Speculative Decoding with KLD Stability for Real-World Serving
par: Yang, Mingyu, et autres
Publié: (2025)

Scalable Engine and the Performance of Different LLM Models in a SLURM based HPC architecture
par: Luiz, Anderson de Lima, et autres
Publié: (2025)

Combining Serverless and High-Performance Computing Paradigms to support ML Data-Intensive Applications
par: Staylor, Mills, et autres
Publié: (2025)

ZenFlow: Enabling Stall-Free Offloading Training via Asynchronous Updates
par: Lan, Tingfeng, et autres
Publié: (2025)

AutoDDL: Automatic Distributed Deep Learning with Near-Optimal Bandwidth Cost
par: Chen, Jinfan, et autres
Publié: (2023)

GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation
par: Ilager, Shashikant, et autres
Publié: (2025)

Scalability Evaluation of HPC Multi-GPU Training for ECG-based LLMs
par: Mileski, Dimitar, et autres
Publié: (2025)

Libra: Unleashing GPU Heterogeneity for High-Performance Sparse Matrix Multiplication
par: Shi, Jinliang, et autres
Publié: (2025)

ConfigSpec: Profiling-Based Configuration Selection for Distributed Edge--Cloud Speculative LLM Serving
par: Li, Xiangchen, et autres
Publié: (2026)

WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching
par: Li, Xiangchen, et autres
Publié: (2026)

Serving LLMs in HPC Clusters: A Comparative Study of Qualcomm Cloud AI 100 Ultra and NVIDIA Data Center GPUs
par: Sada, Mohammad Firas, et autres
Publié: (2025)

StepCache: Step-Level Reuse with Lightweight Verification and Selective Patching for LLM Serving
par: Nouri, Azam
Publié: (2026)

FlashSpread: IO-Aware GPU Simulation of Non-Markovian Epidemic Dynamics via Kernel Fusion
par: Shakeri, Heman, et autres
Publié: (2026)

Evaluating Large Language Models for Workload Mapping and Scheduling in Heterogeneous HPC Systems
par: Sharma, Aasish Kumar, et autres
Publié: (2025)

Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling
par: Luo, Zizhang, et autres
Publié: (2026)

Accelerating Causal Algorithms for Industrial-scale Data: A Distributed Computing Approach with Ray Framework
par: Verma, Vishal, et autres
Publié: (2024)

Spark-LLM-Eval: A Distributed Framework for Statistically Rigorous Large Language Model Evaluation
par: Mitra, Subhadip
Publié: (2026)

CRDT-Based Game State Synchronization in Peer-to-Peer VR
par: Dantas, Abel, et autres
Publié: (2025)

Flash-Fusion: Enabling Expressive, Low-Latency Queries on IoT Sensor Streams with LLMs
par: Patherya, Kausar, et autres
Publié: (2025)

FedMon: Federated eBPF Monitoring for Distributed Anomaly Detection in Multi-Cluster Cloud Environments
par: Zehra, Sehar, et autres
Publié: (2025)

Benchmarking Federated Learning for Throughput Prediction in 5G Live Streaming Applications
par: Dutta, Yuvraj, et autres
Publié: (2025)

DAGER: Exact Gradient Inversion for Large Language Models
par: Petrov, Ivo, et autres
Publié: (2024)

OPTIMUMP2P: Fast and Reliable Gossiping in P2P Networks
par: Nicolaou, Nicolas, et autres
Publié: (2025)